tag:blogger.com,1999:blog-2198942534740642384.post998055421208643968..comments2023-10-24T03:16:41.009-07:00Comments on Econometrics Beat: Dave Giles' Blog: Solution to the Segmented Regression ProblemDave Gileshttp://www.blogger.com/profile/05389606956062019445noreply@blogger.comBlogger10125tag:blogger.com,1999:blog-2198942534740642384.post-43149119688417465982013-10-26T14:04:53.239-07:002013-10-26T14:04:53.239-07:00Not exactly sure, but I have put some early refere...Not exactly sure, but I have put some early references in a new post (26 October 2013, here:<br />http://davegiles.blogspot.ca/2013/10/segmented-regression-some-relatively.htmlDave Gileshttps://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-45955190908290084582013-10-25T13:23:28.302-07:002013-10-25T13:23:28.302-07:00Dave, could you point out the first time that this...Dave, could you point out the first time that this particular trend segmented regression appeared in the literature, if you happen to know? I am very curious to know. Thanks!Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-13329442562323133902013-10-24T20:19:51.059-07:002013-10-24T20:19:51.059-07:00Hah ! :-) :-)
There's a restriction being im...Hah ! :-) :-)<br />There's a restriction being imposed on the parameters, so if this is false, then teh estimator will be biased (& inconsistent). Students - ECON 545, supp. exercises 2!Dave Gileshttps://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-48147464534242367122013-10-24T16:51:46.306-07:002013-10-24T16:51:46.306-07:00The segmented regression idea has been around in t...The segmented regression idea has been around in the stats. literature since the 60's or 70'sDave Gileshttps://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-75644466894163611402013-10-24T03:38:43.496-07:002013-10-24T03:38:43.496-07:00Thanks for the awesome blog, Dave!
If x* is unknow...Thanks for the awesome blog, Dave!<br />If x* is unknown, one can find its least squares estimate by minimizing SSR over a set of candidate thresholds. I believe, in the current example such an estimate, i.e. argmin-SSR(x*), happens to be equal to 24. I hope I got this right.Davidnoreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-50159227689418040742013-10-23T19:47:41.443-07:002013-10-23T19:47:41.443-07:00I maintain that unless you are looking for a regre...I maintain that unless you are looking for a regression that doesn't give you garbage results, my method is the clear winner buddy.<br /><br />Thanks for looking at my attempt. I checked the EViews code and played around, very educational. A nice way of exploring the algebra of forcing the regression surface through a fixed a point, with some dummy variables intuition in there. I think this would be a great problem in most econometrics texts. Have your students already been subjected to this? I wonder about bias, and am curious if you have a DGP in mind for this problem.Anonymoushttps://www.blogger.com/profile/16556840239646258166noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-19668167916056893012013-10-23T16:42:22.467-07:002013-10-23T16:42:22.467-07:00See page 425-426See page 425-426Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-80919343333856426392013-10-23T11:28:35.640-07:002013-10-23T11:28:35.640-07:00This paper may be of some interest.
http://people...This paper may be of some interest. <br />http://people.bu.edu/perron/papers/EJ-06.pdfAnonymousnoreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-85142291050804062862013-10-22T19:45:23.334-07:002013-10-22T19:45:23.334-07:00Mark - yes, this definitely extends to any number ...Mark - yes, this definitely extends to any number of (known) change-points.Dave Gileshttps://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-33827238638730423822013-10-22T16:35:21.236-07:002013-10-22T16:35:21.236-07:00thanks dave. very interesting. you allow for a cha...thanks dave. very interesting. you allow for a changing slope at a known point using the introduction of a dummy variable and a second coefficient. ( dimitry: my mistake. it seems like you were close ) neat stuff. and it also seems like an approach that could be extended to multiple change points ( as long as you know what they are beforehand ) also.<br /><br /><br /><br /><br />mark leedsnoreply@blogger.com